@ephox/polaris - npm Package Compare versions

Comparing version 6.0.9 to 6.1.0-alpha.0

CHANGELOG.md

@@ -9,2 +9,5 @@ # Changelog
 
+### Added
+- New `Words.getWordsWithIndices` API to extract words and their start and end indices when provided an array of characters. #TINY-9654
+
 ## 6.0.2 - 2022-06-29
@@ -11,0 +14,0 @@

lib/main/ts/ephox/polaris/api/Words.d.ts

@@ -1,5 +0,7 @@
-import * as WordOptions from '../words/Words';
-declare type GetWordsApi = <T>(chars: T[], extract: (char: T) => string, options?: WordOptions.WordOptions) => T[][];
+import * as Words from '../words/Words';
+declare type GetWordsApi = <T>(chars: T[], extract: (char: T) => string, options?: Words.WordOptions) => Words.Word<T>[];
 declare const getWords: GetWordsApi;
-export { getWords };
+declare type GetWordsAndIndicesApi = <T>(chars: T[], extract: (char: T) => string, options?: Words.WordOptions) => Words.WordsWithIndices<T>;
+declare const getWordsWithIndices: GetWordsAndIndicesApi;
+export { getWords, getWordsWithIndices };
 //# sourceMappingURL=Words.d.ts.map

lib/main/ts/ephox/polaris/api/Words.js

@@ -1,4 +0,5 @@
-import * as WordOptions from '../words/Words';
-const getWords = WordOptions.getWords;
-export { getWords };
+import * as Words from '../words/Words';
+const getWords = Words.getWords;
+const getWordsWithIndices = Words.getWordsWithIndices;
+export { getWords, getWordsWithIndices };
 //# sourceMappingURL=Words.js.map

lib/main/ts/ephox/polaris/words/UnicodeData.d.ts

@@ -1,2 +0,2 @@
-declare const punctuationStr = "[!-#%-*,-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]";
+declare const punctuationStr = "[~^\u2116|!-*+-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]";
 declare const characterIndices: {
@@ -3,0 +3,0 @@ ALETTER: number;

lib/main/ts/ephox/polaris/words/UnicodeData.js

 /* eslint-disable max-len */
-const punctuationStr = '[!-#%-*,-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]';
+const punctuationStr = `[~^№|!-*+-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]`;
 const regExps = {
@@ -4,0 +4,0 @@ aletter: '[A-Za-z\u00AA\u00B5\u00BA\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02C1\u02C6-\u02D1\u02E0-\u02E4\u02EC\u02EE\u0370-\u0374\u0376\u0377\u037A-\u037D\u0386\u0388-\u038A\u038C\u038E-\u03A1\u03A3-\u03F5\u03F7-\u0481\u048A-\u0527\u0531-\u0556\u0559\u0561-\u0587\u05D0-\u05EA\u05F0-\u05F3\u0620-\u064A\u066E\u066F\u0671-\u06D3\u06D5\u06E5\u06E6\u06EE\u06EF\u06FA-\u06FC\u06FF\u0710\u0712-\u072F\u074D-\u07A5\u07B1\u07CA-\u07EA\u07F4\u07F5\u07FA\u0800-\u0815\u081A\u0824\u0828\u0840-\u0858\u0904-\u0939\u093D\u0950\u0958-\u0961\u0971-\u0977\u0979-\u097F\u0985-\u098C\u098F\u0990\u0993-\u09A8\u09AA-\u09B0\u09B2\u09B6-\u09B9\u09BD\u09CE\u09DC\u09DD\u09DF-\u09E1\u09F0\u09F1\u0A05-\u0A0A\u0A0F\u0A10\u0A13-\u0A28\u0A2A-\u0A30\u0A32\u0A33\u0A35\u0A36\u0A38\u0A39\u0A59-\u0A5C\u0A5E\u0A72-\u0A74\u0A85-\u0A8D\u0A8F-\u0A91\u0A93-\u0AA8\u0AAA-\u0AB0\u0AB2\u0AB3\u0AB5-\u0AB9\u0ABD\u0AD0\u0AE0\u0AE1\u0B05-\u0B0C\u0B0F\u0B10\u0B13-\u0B28\u0B2A-\u0B30\u0B32\u0B33\u0B35-\u0B39\u0B3D\u0B5C\u0B5D\u0B5F-\u0B61\u0B71\u0B83\u0B85-\u0B8A\u0B8E-\u0B90\u0B92-\u0B95\u0B99\u0B9A\u0B9C\u0B9E\u0B9F\u0BA3\u0BA4\u0BA8-\u0BAA\u0BAE-\u0BB9\u0BD0\u0C05-\u0C0C\u0C0E-\u0C10\u0C12-\u0C28\u0C2A-\u0C33\u0C35-\u0C39\u0C3D\u0C58\u0C59\u0C60\u0C61\u0C85-\u0C8C\u0C8E-\u0C90\u0C92-\u0CA8\u0CAA-\u0CB3\u0CB5-\u0CB9\u0CBD\u0CDE\u0CE0\u0CE1\u0CF1\u0CF2\u0D05-\u0D0C\u0D0E-\u0D10\u0D12-\u0D3A\u0D3D\u0D4E\u0D60\u0D61\u0D7A-\u0D7F\u0D85-\u0D96\u0D9A-\u0DB1\u0DB3-\u0DBB\u0DBD\u0DC0-\u0DC6\u0F00\u0F40-\u0F47\u0F49-\u0F6C\u0F88-\u0F8C\u10A0-\u10C5\u10D0-\u10FA\u10FC\u1100-\u1248\u124A-\u124D\u1250-\u1256\u1258\u125A-\u125D\u1260-\u1288\u128A-\u128D\u1290-\u12B0\u12B2-\u12B5\u12B8-\u12BE\u12C0\u12C2-\u12C5\u12C8-\u12D6\u12D8-\u1310\u1312-\u1315\u1318-\u135A\u1380-\u138F\u13A0-\u13F4\u1401-\u166C\u166F-\u167F\u1681-\u169A\u16A0-\u16EA\u16EE-\u16F0\u1700-\u170C\u170E-\u1711\u1720-\u1731\u1740-\u1751\u1760-\u176C\u176E-\u1770\u1820-\u1877\u1880-\u18A8\u18AA\u18B0-\u18F5\u1900-\u191C\u1A00-\u1A16\u1B05-\u1B33\u1B45-\u1B4B\u1B83-\u1BA0\u1BAE\u1BAF\u1BC0-\u1BE5\u1C00-\u1C23\u1C4D-\u1C4F\u1C5A-\u1C7D\u1CE9-\u1CEC\u1CEE-\u1CF1\u1D00-\u1DBF\u1E00-\u1F15\u1F18-\u1F1D\u1F20-\u1F45\u1F48-\u1F4D\u1F50-\u1F57\u1F59\u1F5B\u1F5D\u1F5F-\u1F7D\u1F80-\u1FB4\u1FB6-\u1FBC\u1FBE\u1FC2-\u1FC4\u1FC6-\u1FCC\u1FD0-\u1FD3\u1FD6-\u1FDB\u1FE0-\u1FEC\u1FF2-\u1FF4\u1FF6-\u1FFC\u2071\u207F\u2090-\u209C\u2102\u2107\u210A-\u2113\u2115\u2119-\u211D\u2124\u2126\u2128\u212A-\u212D\u212F-\u2139\u213C-\u213F\u2145-\u2149\u214E\u2160-\u2188\u24B6-\u24E9\u2C00-\u2C2E\u2C30-\u2C5E\u2C60-\u2CE4\u2CEB-\u2CEE\u2D00-\u2D25\u2D30-\u2D65\u2D6F\u2D80-\u2D96\u2DA0-\u2DA6\u2DA8-\u2DAE\u2DB0-\u2DB6\u2DB8-\u2DBE\u2DC0-\u2DC6\u2DC8-\u2DCE\u2DD0-\u2DD6\u2DD8-\u2DDE\u2E2F\u3005\u303B\u303C\u3105-\u312D\u3131-\u318E\u31A0-\u31BA\uA000-\uA48C\uA4D0-\uA4FD\uA500-\uA60C\uA610-\uA61F\uA62A\uA62B\uA640-\uA66E\uA67F-\uA697\uA6A0-\uA6EF\uA717-\uA71F\uA722-\uA788\uA78B-\uA78E\uA790\uA791\uA7A0-\uA7A9\uA7FA-\uA801\uA803-\uA805\uA807-\uA80A\uA80C-\uA822\uA840-\uA873\uA882-\uA8B3\uA8F2-\uA8F7\uA8FB\uA90A-\uA925\uA930-\uA946\uA960-\uA97C\uA984-\uA9B2\uA9CF\uAA00-\uAA28\uAA40-\uAA42\uAA44-\uAA4B\uAB01-\uAB06\uAB09-\uAB0E\uAB11-\uAB16\uAB20-\uAB26\uAB28-\uAB2E\uABC0-\uABE2\uAC00-\uD7A3\uD7B0-\uD7C6\uD7CB-\uD7FB\uFB00-\uFB06\uFB13-\uFB17\uFB1D\uFB1F-\uFB28\uFB2A-\uFB36\uFB38-\uFB3C\uFB3E\uFB40\uFB41\uFB43\uFB44\uFB46-\uFBB1\uFBD3-\uFD3D\uFD50-\uFD8F\uFD92-\uFDC7\uFDF0-\uFDFB\uFE70-\uFE74\uFE76-\uFEFC\uFF21-\uFF3A\uFF41-\uFF5A\uFFA0-\uFFBE\uFFC2-\uFFC7\uFFCA-\uFFCF\uFFD2-\uFFD7\uFFDA-\uFFDC]',

lib/main/ts/ephox/polaris/words/WordBoundary.js

@@ -47,5 +47,12 @@ import { characterIndices as ci } from './UnicodeData';
     // WB4. Ignore format and extend characters.
-    if (type === ci.EXTEND || type === ci.FORMAT ||
-        prevType === ci.EXTEND || prevType === ci.FORMAT ||
-        nextType === ci.EXTEND || nextType === ci.FORMAT) {
+    if ((type === ci.EXTEND || type === ci.FORMAT) &&
+        (nextType === ci.ALETTER || nextType === ci.NUMERIC || nextType === ci.KATAKANA ||
+            nextType === ci.EXTEND || nextType === ci.FORMAT)
+        ||
+            (nextType === ci.EXTEND ||
+                // TINY-9654: Only ignore format characters if they do not precede a word boundary. Since some format characters overlap with whitespace characters (ex: \ufeff) and
+                // our word extraction logic excludes whitespace characters, if a whitespace-overlapping format character that precedes a word boundary is not split on, whichever word
+                // it is a part of will not be added to the list of extracted words, causing inaccuracies.
+                nextType === ci.FORMAT && (nextNextType === ci.ALETTER || nextNextType === ci.NUMERIC || nextNextType === ci.KATAKANA || nextNextType === ci.EXTEND || nextNextType === ci.FORMAT))
+                && (type === ci.ALETTER || type === ci.NUMERIC || type === ci.KATAKANA || type === ci.EXTEND || type === ci.FORMAT)) {
         return false;
@@ -52,0 +59,0 @@ }

lib/main/ts/ephox/polaris/words/Words.d.ts

@@ -0,1 +1,10 @@
+export declare type Word<T> = T[];
+interface WordIndex {
+    readonly start: number;
+    readonly end: number;
+}
+export interface WordsWithIndices<T> {
+    readonly words: Word<T>[];
+    readonly indices: WordIndex[];
+}
 export interface WordOptions {
@@ -5,4 +14,5 @@ includeWhitespace?: boolean;
 }
-declare const getWords: <T>(chars: T[], extract: (char: T) => string, options?: WordOptions) => T[][];
-export { getWords };
+declare const getWordsWithIndices: <T>(chars: Word<T>, extract: (char: T) => string, options?: WordOptions) => WordsWithIndices<T>;
+declare const getWords: <T>(chars: Word<T>, extract: (char: T) => string, options?: WordOptions) => Word<T>[];
+export { getWords, getWordsWithIndices };
 //# sourceMappingURL=Words.d.ts.map

lib/main/ts/ephox/polaris/words/Words.js

@@ -1,2 +0,2 @@
-import { Unicode } from '@ephox/katamari';
+import { Arr } from '@ephox/katamari';
 import { classify } from './StringMapper';
@@ -23,4 +23,5 @@ import * as UnicodeData from './UnicodeData';
 };
-const findWords = (chars, sChars, characterMap, options) => {
+const findWordsWithIndices = (chars, sChars, characterMap, options) => {
     const words = [];
+    const indices = [];
     let word = [];
@@ -48,2 +49,6 @@ // Loop through each character in the classification map and determine whether
                 words.push(word);
+                indices.push({
+                    start: startOfWord,
+                    end: endOfWord
+                });
             }
@@ -53,3 +58,3 @@ word = [];
     }
-    return words;
+    return { words, indices };
 };
@@ -60,3 +65,3 @@ const getDefaultOptions = () => ({
 });
-const getWords = (chars, extract, options) => {
+const getWordsWithIndices = (chars, extract, options) => {
     options = {
@@ -66,16 +71,8 @@ ...getDefaultOptions(),
     };
-    const filteredChars = [];
-    const extractedChars = [];
-    // tslint:disable-next-line:prefer-for-of
-    for (let i = 0; i < chars.length; i++) {
-        const ch = extract(chars[i]);
-        if (ch !== Unicode.zeroWidth) {
-            filteredChars.push(chars[i]);
-            extractedChars.push(ch);
-        }
-    }
+    const extractedChars = Arr.map(chars, extract);
     const characterMap = classify(extractedChars);
-    return findWords(filteredChars, extractedChars, characterMap, options);
+    return findWordsWithIndices(chars, extractedChars, characterMap, options);
 };
-export { getWords };
+const getWords = (chars, extract, options) => getWordsWithIndices(chars, extract, options).words;
+export { getWords, getWordsWithIndices };
 //# sourceMappingURL=Words.js.map

lib/test/ts/atomic/api/WordsTest.js

@@ -44,4 +44,30 @@ import { Assert, UnitTest } from '@ephox/bedrock-client';
     assertWords(['42.6±4.2'], '42.6±4.2');
-    assertWords(['ab'], 'a\ufeffb');
+    // TINY-9654: Does not split on extend characters (ex: \u0300)
+    assertWords(['a\u0300b'], 'a\u0300b');
+    assertWords(['a\u0300bc'], 'a\u0300bc');
+    assertWords(['ab\u0300c'], 'ab\u0300c');
+    assertWords(['a\u0300b', 'c'], 'a\u0300b c');
+    assertWords(['\u0300b'], '\u0300b');
+    assertWords(['a', '\u0300b'], 'a \u0300b');
+    assertWords(['\u0300'], '\u0300');
+    assertWords(['\u0300'], '\u0300 ');
+    assertWords(['a\u0300'], 'a\u0300');
+    assertWords(['a\u0300'], 'a\u0300 ');
+    // TINY-9654: Does not split on format characters (ex: \ufeff) if they do not precede a word boundary
+    // TINY-9654: Does not strip \ufeff characters (obsolete TINY-1166 fix removed)
+    assertWords(['a\ufeffb'], 'a\ufeffb');
+    assertWords(['a\ufeffbc'], 'a\ufeffbc');
+    assertWords(['ab\ufeffc'], 'ab\ufeffc');
+    assertWords(['a\ufeffb', 'c'], 'a\ufeffb c');
+    assertWords(['\ufeffb'], '\ufeffb');
+    assertWords(['a', '\ufeffb'], 'a \ufeffb');
+    // TINY-9654: Split on format characters if they precede a word boundary. Some format characters overlap with whitespace
+    // characters (ex: \ufeff). Since whitespace characters are not extracted, if a whitespace-overlapping format character that
+    // precedes a word boundary is not split on, whichever word it is a part of will not be added to the list of extracted words,
+    // causing inaccuracies.
+    assertWords([], '\ufeff');
+    assertWords([], '\ufeff ');
+    assertWords(['a'], 'a\ufeff');
+    assertWords(['a'], 'a\ufeff ');
 });
 //# sourceMappingURL=WordsTest.js.map

package.json

 {
   "name": "@ephox/polaris",
   "description": "This project does data manipulation on arrays and strings.",
-  "version": "6.0.9",
+  "version": "6.1.0-alpha.0",
   "repository": {
@@ -28,3 +28,2 @@ "type": "git",
   "scripts": {
-    "prepublishOnly": "tsc -b",
     "test": "bedrock-auto -b chrome-headless -d src/test/ts",
@@ -38,4 +37,3 @@ "test-manual": "bedrock -d src/test/ts",
   "module": "./lib/main/ts/ephox/polaris/api/Main.js",
-  "types": "./lib/main/ts/ephox/polaris/api/Main.d.ts",
-  "gitHead": "d0a354c4921b1ce815cfb36cc72ea3a309932fee"
+  "types": "./lib/main/ts/ephox/polaris/api/Main.d.ts"
 }

src/main/ts/ephox/polaris/api/Words.ts

@@ -1,8 +0,12 @@
-import * as WordOptions from '../words/Words';
+import * as Words from '../words/Words';
 
-type GetWordsApi = <T>(chars: T[], extract: (char: T) => string, options?: WordOptions.WordOptions) => T[][];
-const getWords: GetWordsApi = WordOptions.getWords;
+type GetWordsApi = <T>(chars: T[], extract: (char: T) => string, options?: Words.WordOptions) => Words.Word<T>[];
+const getWords: GetWordsApi = Words.getWords;
 
+type GetWordsAndIndicesApi = <T>(chars: T[], extract: (char: T) => string, options?: Words.WordOptions) => Words.WordsWithIndices<T>;
+const getWordsWithIndices: GetWordsAndIndicesApi = Words.getWordsWithIndices;
+
 export {
-  getWords
+  getWords,
+  getWordsWithIndices
 };

src/main/ts/ephox/polaris/words/UnicodeData.ts

 
 /* eslint-disable max-len */
-const punctuationStr = '[!-#%-*,-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]';
+const punctuationStr = `[~^№|!-*+-\\/:;?@\\[-\\]_{}\u00A1\u00AB\u00B7\u00BB\u00BF;\u00B7\u055A-\u055F\u0589\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u3008\u3009\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]`;
 
@@ -5,0 +5,0 @@ const regExps = {

src/main/ts/ephox/polaris/words/WordBoundary.ts

@@ -59,5 +59,12 @@ import { CharacterMap } from './StringMapper';
   // WB4. Ignore format and extend characters.
-  if (type === ci.EXTEND || type === ci.FORMAT ||
-    prevType === ci.EXTEND || prevType === ci.FORMAT ||
-    nextType === ci.EXTEND || nextType === ci.FORMAT) {
+  if ((type === ci.EXTEND || type === ci.FORMAT) &&
+    (nextType === ci.ALETTER || nextType === ci.NUMERIC || nextType === ci.KATAKANA ||
+      nextType === ci.EXTEND || nextType === ci.FORMAT)
+    ||
+    (nextType === ci.EXTEND ||
+      // TINY-9654: Only ignore format characters if they do not precede a word boundary. Since some format characters overlap with whitespace characters (ex: \ufeff) and
+      // our word extraction logic excludes whitespace characters, if a whitespace-overlapping format character that precedes a word boundary is not split on, whichever word
+      // it is a part of will not be added to the list of extracted words, causing inaccuracies.
+      nextType === ci.FORMAT && (nextNextType === ci.ALETTER || nextNextType === ci.NUMERIC || nextNextType === ci.KATAKANA || nextNextType === ci.EXTEND || nextNextType === ci.FORMAT))
+      && (type === ci.ALETTER || type === ci.NUMERIC || type === ci.KATAKANA || type === ci.EXTEND || type === ci.FORMAT)) {
     return false;
@@ -64,0 +71,0 @@ }

src/main/ts/ephox/polaris/words/Words.ts

@@ -1,2 +0,2 @@
-import { Unicode } from '@ephox/katamari';
+import { Arr } from '@ephox/katamari';
 
@@ -29,6 +29,19 @@ import { CharacterMap, classify } from './StringMapper';
 
-const findWords = <T>(chars: T[], sChars: string[], characterMap: CharacterMap, options: WordOptions): T[][] => {
-  const words: T[][] = [];
-  let word: T[] = [];
+export type Word<T> = T[];
 
+interface WordIndex {
+  readonly start: number;
+  readonly end: number;
+}
+
+export interface WordsWithIndices<T> {
+  readonly words: Word<T>[];
+  readonly indices: WordIndex[];
+}
+
+const findWordsWithIndices = <T>(chars: Word<T>, sChars: string[], characterMap: CharacterMap, options: WordOptions): WordsWithIndices<T> => {
+  const words: Word<T>[] = [];
+  const indices: WordIndex[] = [];
+  let word: Word<T> = [];
+
   // Loop through each character in the classification map and determine whether
@@ -61,2 +74,6 @@ // it precedes a word boundary, building an array of distinct words as we go.
         words.push(word);
+        indices.push({
+          start: startOfWord,
+          end: endOfWord
+        });
       }
@@ -68,3 +85,3 @@
 
-  return words;
+  return { words, indices };
 };
@@ -82,3 +99,3 @@
 
-const getWords = <T>(chars: T[], extract: (char: T) => string, options?: WordOptions): T[][] => {
+const getWordsWithIndices = <T>(chars: Word<T>, extract: (char: T) => string, options?: WordOptions): WordsWithIndices<T> => {
   options = {
@@ -88,21 +105,13 @@ ...getDefaultOptions(),
   };
-
-  const filteredChars: T[] = [];
-  const extractedChars: string[] = [];
-
-  // tslint:disable-next-line:prefer-for-of
-  for (let i = 0; i < chars.length; i++) {
-    const ch = extract(chars[i]);
-    if (ch !== Unicode.zeroWidth) {
-      filteredChars.push(chars[i]);
-      extractedChars.push(ch);
-    }
-  }
-
+  const extractedChars: string[] = Arr.map(chars, extract);
   const characterMap: CharacterMap = classify(extractedChars);
-  return findWords(filteredChars, extractedChars, characterMap, options);
+  return findWordsWithIndices(chars, extractedChars, characterMap, options);
 };
 
+const getWords = <T>(chars: Word<T>, extract: (char: T) => string, options?: WordOptions): Word<T>[] =>
+  getWordsWithIndices(chars, extract, options).words;
+
 export {
-  getWords
+  getWords,
+  getWordsWithIndices
 };

src/test/ts/atomic/api/WordsTest.ts

@@ -55,3 +55,32 @@ import { Assert, UnitTest } from '@ephox/bedrock-client';
   assertWords([ '42.6±4.2' ], '42.6±4.2');
-  assertWords([ 'ab' ], 'a\ufeffb');
+
+  // TINY-9654: Does not split on extend characters (ex: \u0300)
+  assertWords([ 'a\u0300b' ], 'a\u0300b');
+  assertWords([ 'a\u0300bc' ], 'a\u0300bc');
+  assertWords([ 'ab\u0300c' ], 'ab\u0300c');
+  assertWords([ 'a\u0300b', 'c' ], 'a\u0300b c');
+  assertWords([ '\u0300b' ], '\u0300b');
+  assertWords([ 'a', '\u0300b' ], 'a \u0300b');
+  assertWords([ '\u0300' ], '\u0300');
+  assertWords([ '\u0300' ], '\u0300 ');
+  assertWords([ 'a\u0300' ], 'a\u0300');
+  assertWords([ 'a\u0300' ], 'a\u0300 ');
+
+  // TINY-9654: Does not split on format characters (ex: \ufeff) if they do not precede a word boundary
+  // TINY-9654: Does not strip \ufeff characters (obsolete TINY-1166 fix removed)
+  assertWords([ 'a\ufeffb' ], 'a\ufeffb');
+  assertWords([ 'a\ufeffbc' ], 'a\ufeffbc');
+  assertWords([ 'ab\ufeffc' ], 'ab\ufeffc');
+  assertWords([ 'a\ufeffb', 'c' ], 'a\ufeffb c');
+  assertWords([ '\ufeffb' ], '\ufeffb');
+  assertWords([ 'a', '\ufeffb' ], 'a \ufeffb');
+
+  // TINY-9654: Split on format characters if they precede a word boundary. Some format characters overlap with whitespace
+  // characters (ex: \ufeff). Since whitespace characters are not extracted, if a whitespace-overlapping format character that
+  // precedes a word boundary is not split on, whichever word it is a part of will not be added to the list of extracted words,
+  // causing inaccuracies.
+  assertWords([ ], '\ufeff');
+  assertWords([ ], '\ufeff ');
+  assertWords([ 'a' ], 'a\ufeff');
+  assertWords([ 'a' ], 'a\ufeff ');
 });

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

No v1

Quality

Package is not semver >=1. This means it is not stable and does not support ^ ranges.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

253497

increased by2.88%

Lines of code

3844

increased by2.32%

Worsened metrics

Number of package files

239

decreased by-0.42%

Number of low quality alerts

2

increased by100%

No dependency changes